vix.ing · top · new · best · stats · spec

Contrastive Hierarchical Discourse Graph for Scientific Document Summarization

2023/05/31 by Haopeng Zhang, Xiao Liu, Zhang, Haopeng +3 · 1 citation
Computer Science · Biochemistry, Genetics and Molecular Biology · #Topic Modeling #Advanced Text Analysis Techniques #Biomedical Text Mining and Ontologies

paper · pdf · doi:10.48550/arxiv.2306.00177

Abstract

The extended structural context has made scientific paper summarization a challenging task. This paper proposes CHANGES, a contrastive hierarchical graph neural network for extractive scientific paper summarization. CHANGES represents a scientific paper with a hierarchical discourse graph and learns effective sentence representations with dedicated designed hierarchical graph information aggregation. We also propose a graph contrastive learning module to learn global theme-aware sentence representations. Extensive experiments on the PubMed and arXiv benchmark datasets prove the effectiveness of CHANGES and the importance of capturing hierarchical structure information in modeling scientific papers.

Cited by

Related